EUVIMEDEUVIMED entdecken
Crossref

Dynamic Adaptive Collaboration for Personalized Federated Learning

LiXin Qin, ChunLong Yao, Ying Li

Intelligenza Artificiale · 2026

DOI: 10.1177/17248035251367166 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Intelligenza Artificiale, 2026. Verfasst von LiXin Qin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of AI-driven personalized services, model training increasingly depends on highly sensitive user-side data, such as location, social behaviour, and biometric information. These data not only exhibit pronounced non-independent and identically distributed (non-IID) characteristics but also pose serious privacy risks when processed centrally. Achieving efficient personalized modelling while preserving data locality and privacy has thus become a critical challenge in the evolution of personalized AI. In recent years, personalized federated learning (PFL) has gained significant attention for its strong performance in addressing non-IID data challenges. However, existing approaches often fall short in effectively balancing collaborative efficiency with personalization. To overcome this limitation, we propose FedDAC, a dynamically adaptive, collaboration-enhanced personalized federated learning method. By quantitatively assessing the responsiveness of each parameter to non-IID data, FedDAC dynamically selects collaborative clients, ensuring effective cooperation while retaining personalized feature information. Extensive experiments on four benchmark datasets (EMNIST, CIFAR-10, CIFAR-100, and Tiny ImageNet) under two pathological non-IID settings show that FedDAC consistently outperforms strong baselines. It improves accuracy by 1.5–3.2% on average, reaching 5.9% on highly heterogeneous tasks. The source code is publicly available at https://github.com/Lixinqin9/FedDAC-MAIN .

Zitieren

APA

Qin, L., Yao, C., & Li, Y. (2026). Dynamic Adaptive Collaboration for Personalized Federated Learning. Intelligenza Artificiale. https://doi.org/10.1177/17248035251367166

Vancouver

Qin L, Yao C, Li Y. Dynamic Adaptive Collaboration for Personalized Federated Learning. Intelligenza Artificiale. 2026. doi:10.1177/17248035251367166

BibTeX
@article{Qin2026,
  author = {Qin, LiXin and Yao, ChunLong and Li, Ying},
  title = {Dynamic Adaptive Collaboration for Personalized Federated Learning},
  journal = {Intelligenza Artificiale},
  year = {2026},
  doi = {10.1177/17248035251367166}
}
Kostenlos starten →